# A Comparative Benchmark of a Moroccan Darija Toxicity Detection Model (Typica.ai) and Major LLM-Based Moderation APIs (OpenAI, Mistral, Anthropic)

arXiv: https://arxiv.org/abs/2505.04640 · HTML: https://mlsanity.com/paper/2505.04640/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 13 references that are in the map.
- First posted on arXiv 5 May 2025.

## Builds on (most cited first, 2 of 2)

- [GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP](https://mlsanity.com/paper/2305.14976/) (2023)
- [Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties](https://mlsanity.com/paper/2411.10954/) (2024)

## Abstract (arXiv)

This paper presents a comparative benchmark evaluating the performance of Typica.ai's custom Moroccan Darija toxicity detection model against major LLM-based moderation APIs: OpenAI (omni-moderation-latest), Mistral (mistral-moderation-latest), and Anthropic Claude (claude-3-haiku-20240307). We focus on culturally grounded toxic content, including implicit insults, sarcasm, and culturally specific aggression often overlooked by general-purpose systems. Using a balanced test set derived from the OMCD_Typica.ai_Mix dataset, we report precision, recall, F1-score, and accuracy, offering insights into challenges and opportunities for moderation in underrepresented languages. Our results highlight Typica.ai's superior performance, underlining the importance of culturally adapted models for reliable content moderation.